1
ComplianceAgent: Open-source EU AI Act compliance scanner
一键扫描你的AI项目是否符合欧盟AI法案合规要求，开源免费5秒出结果
Article URL: https://github.com/latreon/compliance-agent Comments URL: https://news.ycombinator.com/item?id=48793704 Points: 1 # Comments: 0
2
Civil Court Simulation with Large Language Models
用大语言模型模拟民事法庭审判，AI辅助司法系统迈向新可能。
arXiv:2606.09632v1 Announce Type: new Abstract: Court simulation bridges legal education and judicial practice, yet human-based simulations are costly…
3
LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks
为开放法律任务设计的评分标准引导诊断基准，提升法律AI系统评估的可靠性和可解释性。
arXiv:2606.09389v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the rel…
4
Can You Trust What You See? Human and AI Detection of Synthetic Legal Evidence
论文探讨人类与AI在识别合成法律证据上的可信度差异，揭示AI检测的挑战与局限。
arXiv:2606.07613v1 Announce Type: new Abstract: Visual evidence has long been treated as a reliable form of legal proof, but advances in artificial in…
5
Show HN: Open-source, local-first legal AI workspace for lawyers
开源且本地优先的法律AI工作空间，律师可以安全高效地处理文档与案件。
Article URL: https://github.com/rohasnagpal/AI-Blueprint Comments URL: https://news.ycombinator.com/item?id=48457883 Points: 2 # Comments: 0
6
Parthenon Law: A Self-Evolving Legal-Agent Framework
法律AI代理新框架，自我进化解决端到端法律事务的三大障碍。
arXiv:2606.04602v1 Announce Type: new Abstract: As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into revie…
7
Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs
用法律引用图检测和减少大模型编造法律条文的问题，提升AI可信度。
arXiv:2606.00898v1 Announce Type: new Abstract: Large language models systematically hallucinate legal citations -- fabricating statute references, ci…
8
Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning
法律AI可信度研究新突破，提出相关性敏感评估与求解器推理结合的评估框架。
arXiv:2605.26530v1 Announce Type: new Abstract: Legal reasoning requires distinguishing changes that matter from those that do not. Legal AI should re…
9
Maat: The Agentic Legal Research Assistant for Competition Protection
专为竞争保护打造的法律AI研究助手，能智能检索与分析法规，效率惊人！
arXiv:2605.27331v1 Announce Type: new Abstract: Competition law experts conducting legal research must review extensive volumes of cases, decisions, a…
10
Orchestration problems hurt legal AI
揭示法律AI的核心困境——编排问题如何拖累应用，法律科技从业者必看。
Article URL: https://lexifina.com/blog/legal-ontologies-for-ai Comments URL: https://news.ycombinator.com/item?id=48256327 Points: 1 # Comments: 0
11
Fine-grained Claim-level RAG Benchmark for Law
面向法律领域的细粒度声明级RAG基准，评估模型事实检索与推理能力的新方法。
arXiv:2605.21071v1 Announce Type: new Abstract: The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answe…
12
Exploring Lightweight Large Language Models for Court View Generation
轻量级大模型在法律AI中展现潜力，这篇论文系统探索了小于2B参数模型在法院观点生成任务上的表现。
arXiv:2605.16770v1 Announce Type: new Abstract: Criminal Court View Generation (CVG) is a critical task in Legal Artificial Intelligence (Legal AI), i…
13
Customizing models for legal professionals
OpenAI联手法律AI公司Harvey，打造专为法律人定制的智能模型，赋能法律行业新效率
Harvey partners with OpenAI to build a custom-trained model for legal professionals.